\(\mathrm{contacts} \sim \mathrm{NegBin(\mu, k)}\)
| Model | Δ DIC |
|---|---|
| Collective | 0 |
| Individual | -5k |
\(\mathrm{contacts} \sim \mathrm{NegBin(\mu, k)}\)
\(\log(\mu) = \alpha + \beta_\mathrm{a} \cdot \mathrm{age} + \ldots\)
\(\mathrm{contacts} \sim \mathrm{NegBin(\mu, k)}\)
| Model | Δ DIC |
|---|---|
| Collective | 0 |
| Individual | -5k |
| Covariate | -50k |
| Covariate individual | -52k |
\(\mathrm{ili} \sim \mathrm{Binomial(1, p)}\)
| Model | Δ DIC |
|---|---|
| Collective | 0 |
| Collective + contacts | +4 |
| Individual | +3k |
| Covariate | -21 |
| Covariate individual | -42 |
\(\mathrm{ili} \sim \mathrm{Binomial(1, p)}\)
\(\mathrm{logit}(p) = \alpha + \beta_\mathrm{a} \cdot \mathrm{age} + \ldots\)
\(\beta_{ij}(t)\) varying stochastically, estimated as part of inference.
Ken Eames, John Edmunds
The Flusurvey and Influenzanet teams and participants